HAIL.SO / DISPATCH · 2026-07-11 · COMPARE
FILE: COMPARE · 6 of 6 slots

side by side.

← all costsclear
01

Large language models

1 model
Perplexity
Sonar
×
Output $/MTok$1.00
Input $/MTok$1.00
Cached input $/MTok
Context window128,000
Output cap8,000
Modalitiesin: text / out: text
Tool use
Structured output
FamilySonar
Knowledge cutoff
Verified2026-07-02
Sourceprovider page ↗
02

Speech to text

1 model
AssemblyAI
Universal-2
×
$/min$0.002500
$/min batch
Streaming
Realtime
Languages99+
Diarizationextra-cost
TTFW
Verified2026-07-02
Sourceprovider page ↗
03

Text to speech

4 models
Deepgram
Deepgram Aura 2
×
Smallest.ai
Lightning v3.1
×
Cartesia
Sonic 2
×
Rime
Rime Mist v3
×
$/1M chars$30.00$17.50$50.00$30.00
Voice qualityneuralneuralneuralneural
Voice cloning✓ included✓ included
Voice count21794
Languagesen, es, de, fr, nl, it, jaen, hi, es, mr, kn, ta, bn, gu, te, ml, pa, oren, fr, de, es, pt, zh, ja, koen
SSML support
TTFB200ms90ms37ms
Output formatswav, mp3, linear16, mulaw, alaw, opuspcm, mp3, wav, ulaw, alaw
Verified2026-07-022026-07-022026-07-022026-07-02
Sourceprovider page ↗provider page ↗provider page ↗provider page ↗